CN113849921B - Method for evaluating pretreatment effect of large data sample of wear of cutter of tunneling machine - Google Patents
Method for evaluating pretreatment effect of large data sample of wear of cutter of tunneling machine Download PDFInfo
- Publication number
- CN113849921B CN113849921B CN202110774098.6A CN202110774098A CN113849921B CN 113849921 B CN113849921 B CN 113849921B CN 202110774098 A CN202110774098 A CN 202110774098A CN 113849921 B CN113849921 B CN 113849921B
- Authority
- CN
- China
- Prior art keywords
- sample
- pretreatment
- prediction
- data sample
- cutter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000005641 tunneling Effects 0.000 title claims abstract description 34
- 230000000694 effects Effects 0.000 title claims abstract description 10
- 238000005299 abrasion Methods 0.000 claims abstract description 22
- 238000002203 pretreatment Methods 0.000 claims abstract description 16
- 238000011156 evaluation Methods 0.000 claims abstract description 13
- 238000012937 correction Methods 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims description 26
- 238000013507 mapping Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000013139 quantization Methods 0.000 abstract 1
- 239000011435 rock Substances 0.000 description 6
- 238000010276 construction Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 239000002131 composite material Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000012314 multivariate regression analysis Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Geometry (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
A method for evaluating the pre-treatment effect of a tunneling machine cutter abrasion big data sample belongs to the technical field of tunneling machine cutter abrasion control in underground engineering technology, in order to quantitatively evaluate the effectiveness of different data pre-treatment means and the generalization capability of a corresponding cutter abrasion prediction model, physical quantity abstraction treatment, factor influence quantitative correction, structure statistic, fitting and empirical analysis are taken as technical means, pre-treatment geometric depth, structure cross-sample error ratio, correction error ratio influence factor, structure pre-treatment depth applicability cross-sample evaluation index and optimized pre-treatment depth of the tunneling machine cutter abrasion big data sample are defined as implementation steps, the quantization degree and the interpretability of the tunneling machine cutter abrasion big data sample pre-treatment method can be improved, and a calculation basis is provided for quantitatively evaluating the advantages and disadvantages of various tunneling machine cutter abrasion big data sample pre-treatment methods and optimizing proper data pre-treatment methods, the method is reasonable and has strong practicability.
Description
Technical Field
The invention relates to the technical field of wear control of a tunneling machine cutter in the technical field of underground engineering, in particular to a method for evaluating pretreatment effect of a tunneling machine cutter wear big data sample.
Background
The wear of the cutter of the heading machine is influenced by various factors such as the rock hardness degree, the thrust, the torque, the heading mileage and the like, so in order to obtain the statistical relationship between the sample of the wear amount of the cutter of the heading machine, which is actually measured in a construction site, and various factors such as the rock hardness degree, the thrust, the torque, the heading mileage and the like, statistical learning analysis is often performed by methods such as multivariate regression analysis, deep learning and the like.
However, the statistical model obtained by the methods of multiple regression analysis, deep learning and the like only reflects the mathematical relationship between sample values, and the generalization capability and the interpretability of the model are insufficient.
In order to improve generalization capability and interpretability of a prediction model of the wear loss of the cutter of the heading machine, the current pretreatment method of the wear loss of the cutter of the heading machine comprises the following steps:
dividing the abrasion loss by the rock breaking volume by a layering summation method (publication number: CN107180016A, publication date: 2017-09-19) for predicting the abrasion loss of the hob by using an abrasion specific loss index for pretreatment;
(Qinying, Zhanzhuqing, Sun Shachongchuan, etc.. TBM hob abrasion analysis and prediction based on field test [ J ] tunnel construction (Chinese and English), 2019, volume 39 (11): 1914-1921.) wear amount data is divided by the circumference of rock breaking track for pretreatment;
(Zhuweibin, King Hui, Jujian. composite stratum shield hob abrasion cause analysis and countermeasure [ J ] modern tunnel technology, 2006(04): 75-79 +85.) abrasion amount data is directly used as a dependent variable sample without pretreatment.
In order to eliminate the influence of the self-property difference of the rock and the consumed calculation resource difference on the applicability evaluation of the pretreatment method and scientifically and quantitatively evaluate the applicability of the pretreatment depths of various hob abrasion losses in different strata, an index capable of comparing and predicting the applicability of the method across samples needs to be constructed.
The existing sample value comparison indexes, such as arithmetic mean, variance, deviation and other statistics, are not influenced by the sample mean level on the sample value comparison indexes, but the size difference of the wear prediction deviation absolute value of the tunneling machine cutter in different stratums is large and is greatly influenced by stratum conditions, if the indexes are directly used for evaluating and predicting methods for evaluation, the calculated statistic value cannot reflect the accuracy of the predicting method, namely the existing statistics cannot be subjected to cross-sample comparison.
Therefore, in the tool wear amount sample preprocessing means of the tunneling machine, various data preprocessing means exist only sporadically at present, and indexes and methods for evaluating the effectiveness of different data preprocessing means and the generalization capability of corresponding tool wear prediction models are lacked.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a method for evaluating the pretreatment effect of a tunneling machine cutter abrasion big data sample, which has the performance of scientifically and quantitatively evaluating the applicability of pretreatment depths of various hob abrasion loss in different stratums by eliminating the influence of the self-property difference and the consumed calculation resource difference of rocks on the applicability evaluation of the pretreatment method.
The method comprises the following steps:
firstly, defining the pre-processing geometric depth of a tool wear big data sample;
constructing a cross-sample error ratio;
correcting error ratio influence factors;
fourthly, constructing a pre-treatment depth applicability cross-sample evaluation index;
and step five, optimizing the pretreatment depth.
Further, the first step is specifically as follows: dividing the wear loss of the cutter of the tunneling machine by 1 to obtain a pretreatment geometric depth for pretreatment of a cutter wear data sample, and defining the pretreatment geometric depth as a pretreatment geometric depth level 0 of a big data sample;
dividing the wear loss of the cutter of the tunneling machine by the length physical quantity to carry out pretreatment geometric depth of the cutter wear data sample, and defining the pretreatment geometric depth as 1 level of the pretreatment geometric depth of the big data sample;
dividing the wear loss of the cutter of the tunneling machine by the physical area quantity to carry out pretreatment geometric depth of the cutter wear data sample, and defining the pretreatment geometric depth as 2 levels of the pretreatment geometric depth of the big data sample;
and dividing the wear loss of the cutter of the tunneling machine by the volume physical quantity to carry out pretreatment geometric depth of the cutter wear data sample, and defining the pretreatment geometric depth as 3 levels of the pretreatment geometric depth of the big data sample.
Further, the second step is specifically as follows: through providing a cross-sample error ratio Re, as shown in formula (1), the Re removes the influence of dimensional units, becomes a dimensionless expression and becomes a pure number, eliminates the influence of a sample mean level on a sample value comparison index, and transforms a simple mean square error into Re, namely error evaluation statistic which can carry out cross-sample comparison, so that indexes of different units or orders of magnitude can be placed under the same order of magnitude for comparison and weighting;
evaluating the size difference of prediction precision of different heading machine tool wear prediction models in different stratums and the generalization capability of the prediction method by using Re;
in equation (1), MSE is the mean square error obtained after a prediction method is applied to a group of samples,
avg is the arithmetic mean of the absolute values of the measured values of the samples in a group of samples.
Further, the third step is specifically: defining a prediction model to predict a group of actual measurement samples and obtain the whole process of a prediction result as a primary prediction operation;
when different prediction models are applied to different samples, the difference of prediction precision not only has different factors of data preprocessing methods, but also has precision difference caused by the difference of consumed computing resources;
correcting the difference of the computing resource consumption of Re according to the formula (2) to obtain a cross-sample correction error ratio CRe, wherein rc is the total amount of the computing resources consumed by the same prediction operation;
the total amount of computing resources consumed by one prediction operation can be the total main frequency of the CPU occupied by the prediction operation in an accumulated way;
CRe＝Re×rc (2)
the CRe has corrected the computational resource variation factors in Re, and the CRe can represent the applicability of a data preprocessing method to a stratum.
Further, the fourth step is specifically: defining CRea as an arithmetic average value of CRe in a sample space, which is obtained after a prediction model is applied to the prediction of the sample measured values of all the stratums in the sample space, and sCRe is a standard deviation of CRe distribution in the sample space, which is obtained after a prediction model is applied to the prediction of the sample measured values of all the stratums in the sample space;
the method has the advantages that the cross-sample evaluation index SIMS of the pretreatment depth applicability is constructed, as shown in formula (3), the influence of the error distribution discrete degree on the generalization capability of the pretreatment method is taken into account while the error average level is considered;
therefore, the SIMS index can reflect the universality of the data preprocessing method of the prediction models of the abrasion loss of the different heading machines under the condition of multiple types of samples with large average level difference;
SIMS＝|CRea+sCRe| (3)。
further, the fifth step is specifically: and counting to obtain the mapping relation between the SIMS of various prediction models and the pretreatment geometric depth level numerical value of the big data sample, fitting the mapping relation in a sample space to obtain the SIMS prediction model taking the pretreatment geometric depth level numerical value of the big data sample as input and the SIMS as output, and taking the pretreatment geometric depth of the big data sample when the SIMS in the sampling space is the minimum value as the optimal pretreatment depth.
Detailed description of the invention
The invention discloses a method for evaluating the pretreatment effect of a tunneling machine cutter abrasion big data sample, which comprises the following steps:
step one, defining the pre-processing geometric depth of a cutter abrasion big data sample
Various tunneling machine cutter wear prediction models and tunneling machine cutter wear amount sample pretreatment methods corresponding to the various prediction models are counted from the existing documents.
The method comprises the steps of counting existing samples of the abrasion loss of the cutter of the tunneling machine obtained in different stratums through actual measurement, enabling the samples of the abrasion loss of the cutter of the tunneling machine obtained in the same stratums to belong to the same group of samples, and enabling the samples of all groups in the counting category to jointly form a sample space.
And dividing the wear loss of the cutter of the tunneling machine by 1 to obtain a pretreatment geometric depth for pretreatment of the cutter wear data sample, and defining the pretreatment geometric depth as 0 level of the pretreatment geometric depth of the big data sample.
And dividing the wear loss of the cutter of the tunneling machine by the length physical quantity to carry out pretreatment geometric depth of the cutter wear data sample, and defining the pretreatment geometric depth of the big data sample as level 1.
And dividing the wear loss of the cutter of the tunneling machine by the physical area quantity to carry out pretreatment geometrical depth of the cutter wear data sample, and defining the pretreatment geometrical depth of the big data sample to be 2 grades.
And dividing the wear loss of the cutter of the tunneling machine by the volume physical quantity to carry out pretreatment geometric depth of the cutter wear data sample, and defining the pretreatment geometric depth as 3 levels of the pretreatment geometric depth of the big data sample.
Step two construct cross-sample error ratio
Through the fact that the cross-sample error ratio Re is provided, as shown in formula (1), the Re removes the influence of dimensional units, becomes a dimensionless expression and becomes a pure number, the influence of a sample mean level on a sample value comparison index is eliminated, a simple mean square error is transformed into Re, the error evaluation statistic which can be used for cross-sample comparison, and therefore indexes of different units or orders of magnitude can be compared and weighted under the same order of magnitude.
Therefore, the Re can be used for evaluating the size difference of the prediction accuracy of different heading machine tool wear prediction models in different strata and the generalization capability of the prediction method. In the formula (1), MSE is a mean square error obtained by applying a prediction method to the prediction of a group of samples, and avg is an arithmetic mean of absolute values of measured values of the samples in the group of samples.
Correcting the error ratio influencing factor in the third step
And defining a prediction model to predict a group of measured samples and obtain a prediction result as a primary prediction operation.
When different prediction models are applied to different samples, the difference of prediction precision not only has different factors of data preprocessing methods, but also has precision difference caused by the difference of consumed computing resources.
Therefore, Re is corrected for differences in computational resource consumption according to equation (2), and the cross-sample correction error ratio CRe, rc is the total amount of computational resources consumed by the same prediction operation.
The total amount of computing resources consumed by one prediction operation can be the total main frequency of a CPU (central processing unit) of the computer occupied by the prediction operation in an accumulated way.
CRe＝Re×rc (2)。
The CRe has corrected the computational resource variation factors in Re, and the CRe can represent the applicability of a data preprocessing method to a stratum.
Cross-sample evaluation index of depth applicability of four-step structure pretreatment
The CRea is defined as the arithmetic mean value of each CRe in the sample space obtained after a prediction model is applied to the prediction of the sample measured values of all the stratums in the sample space, and the sCRe is the standard deviation of the distribution of each CRe in the sample space obtained after a prediction model is applied to the prediction of the sample measured values of all the stratums in the sample space.
The cross-sample evaluation index SIMS of the depth applicability of the pre-processing is constructed, as shown in formula (3), while the average error level is considered, the influence of the dispersion degree of error distribution on the generalization capability of the pre-processing method is taken into account.
When the SIMS is increased, the universality of the corresponding data preprocessing method is reduced, and when the SIMS is reduced, the universality of the corresponding data preprocessing method is enhanced.
Therefore, the SIMS index can reflect the universality of the data preprocessing method of the model for predicting the wear loss of the cutter of the different tunneling machines under the conditions of multiple types of samples with large average level difference.
SIMS＝|CRea+sCRe| (3)。
Step five, optimizing the pretreatment depth
And carrying out statistics to obtain the mapping relation between the SIMS of various prediction models and the pre-processing geometric depth level numerical value of the large data sample, fitting the mapping relation in the sample space to obtain the SIMS prediction model taking the pre-processing geometric depth level numerical value of the large data sample as input and the SIMS as output, and taking the pre-processing geometric depth of the large data sample when the SIMS in the sampling space is the minimum value as the optimal pre-processing depth.
Claims (4)
1. A method for evaluating the pretreatment effect of a tunneling machine cutter abrasion big data sample is characterized by comprising the following steps:
firstly, defining the pre-processing geometric depth of a tool wear big data sample;
dividing the wear loss of the cutter of the tunneling machine by 1 to obtain a pretreatment geometric depth for pretreatment of a cutter wear data sample, and defining the pretreatment geometric depth as a pretreatment geometric depth level 0 of a big data sample;
dividing the wear loss of the cutter of the tunneling machine by the length physical quantity to carry out pretreatment geometric depth of the cutter wear data sample, and defining the pretreatment geometric depth as 1 level of the pretreatment geometric depth of the big data sample;
dividing the wear loss of the cutter of the tunneling machine by the physical area quantity to carry out pretreatment geometric depth of the cutter wear data sample, and defining the pretreatment geometric depth as 2 levels of the pretreatment geometric depth of the big data sample;
dividing the wear loss of the cutter of the tunneling machine by the volume physical quantity to carry out pretreatment geometric depth of the cutter wear data sample, and defining the pretreatment geometric depth as 3 levels of the pretreatment geometric depth of the big data sample;
constructing a cross-sample error ratio;
correcting error ratio influence factors;
fourthly, constructing a pre-treatment depth applicability cross-sample evaluation index;
defining CRea as an arithmetic average value of CRe in a sample space, which is obtained after a prediction model is applied to the prediction of the sample measured values of all the stratums in the sample space, and sCRe is a standard deviation of CRe distribution in the sample space, which is obtained after a prediction model is applied to the prediction of the sample measured values of all the stratums in the sample space;
the method has the advantages that the cross-sample evaluation index SIMS of the pretreatment depth applicability is constructed, as shown in formula (3), the influence of the error distribution discrete degree on the generalization capability of the pretreatment method is taken into account while the error average level is considered;
therefore, the SIMS index can reflect the universality of the data preprocessing method of the prediction models of the abrasion loss of the different heading machines under the condition of multiple types of samples with large average level difference;
and step five, optimizing the pretreatment depth.
2. The method for evaluating the preprocessing effect of the big data sample of the wearing of the cutter of the tunneling machine according to claim 1, which is characterized in that the second step is as follows:
through providing a cross-sample error ratio Re, as shown in formula (1), the Re removes the influence of dimensional units, becomes a dimensionless expression and becomes a pure number, eliminates the influence of a sample mean level on a sample value comparison index, transforms a simple mean square error into the Re, and performs error evaluation statistics of cross-sample comparison, so that indexes of different units or orders of magnitude can be compared and weighted under the same order of magnitude;
evaluating the size difference of prediction precision of different heading machine tool wear prediction models in different stratums and the generalization capability of the prediction method by using Re;
in the formula (1), MSE is a mean square error obtained by applying a prediction method to the prediction of a group of samples, and avg is an arithmetic mean of absolute values of measured values of the samples in the group of samples.
3. The method for evaluating the preprocessing effect of the big data sample of the wearing of the cutter of the tunneling machine according to claim 1, which is characterized in that the third step is as follows:
defining a prediction model to predict a group of actual measurement samples and obtain the whole process of a prediction result as a primary prediction operation;
when different prediction models are applied to different samples, the difference of prediction precision not only has different factors of data preprocessing methods, but also has precision difference caused by the difference of consumed computing resources;
correcting the difference of the computing resource consumption of Re according to the formula (2) to obtain a cross-sample correction error ratio CRe, wherein rc is the total amount of the computing resources consumed by the same prediction operation;
the total amount of computing resources consumed by one prediction operation can be the total main frequency of the CPU occupied by the prediction operation in an accumulated way;
the CRe has corrected the computing resource difference factor in Re, and the CRe can represent the applicability of a data preprocessing method to a stratum.
4. The method for evaluating the preprocessing effect of the large data sample of the wear of the cutter of the tunneling machine according to claim 1, which is characterized in that the fifth step is as follows:
and counting to obtain the mapping relation between the SIMS of various prediction models and the pretreatment geometric depth level numerical value of the big data sample, fitting the mapping relation in a sample space to obtain the SIMS prediction model taking the pretreatment geometric depth level numerical value of the big data sample as input and the SIMS as output, and taking the pretreatment geometric depth of the big data sample when the SIMS in the sampling space is the minimum value as the optimal pretreatment depth.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110774098.6A CN113849921B (en) | 2021-07-08 | 2021-07-08 | Method for evaluating pretreatment effect of large data sample of wear of cutter of tunneling machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110774098.6A CN113849921B (en) | 2021-07-08 | 2021-07-08 | Method for evaluating pretreatment effect of large data sample of wear of cutter of tunneling machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113849921A CN113849921A (en) | 2021-12-28 |
| CN113849921B true CN113849921B (en) | 2022-06-10 |
Family
ID=78975101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110774098.6A Active CN113849921B (en) | 2021-07-08 | 2021-07-08 | Method for evaluating pretreatment effect of large data sample of wear of cutter of tunneling machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113849921B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378069A (en) * | 2019-08-01 | 2019-10-25 | 南京坤拓土木工程科技有限公司 | A method of prediction boring machine cutter accumulated quality loss late |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5305836A (en) * | 1992-04-08 | 1994-04-26 | Baroid Technology, Inc. | System and method for controlling drill bit usage and well plan |
| US7901863B2 (en) * | 2004-01-27 | 2011-03-08 | Asahi Kasei Chemicals Corporation | Photosensitive resin composition for laser engravable printing substrate |
| US20070244595A1 (en) * | 2006-04-18 | 2007-10-18 | U.I.T., Llc | Method and means for ultrasonic impact machining of surfaces of machine components |
| MY157452A (en) * | 2009-08-07 | 2016-06-15 | Exxonmobil Upstream Res Co | Methods to estimate downhole drilling vibration amplitude from surface measurement |
| NL2016859B1 (en) * | 2016-05-30 | 2017-12-11 | Engie Electroproject B V | A method of and a device for estimating down hole speed and down hole torque of borehole drilling equipment while drilling, borehole equipment and a computer program product. |
| CN107180016B (en) * | 2017-05-23 | 2018-08-24 | 南京工业大学 | Using the layering summation of abrasion specific consumption exponential forecasting hob abrasion amount |
| CN109571141A (en) * | 2018-11-01 | 2019-04-05 | 北京理工大学 | A kind of Monitoring Tool Wear States in Turning based on machine learning |
| CN110059442B (en) * | 2019-05-07 | 2020-08-14 | 同济大学 | Turning tool changing method based on part surface roughness and power information |
-
2021
- 2021-07-08 CN CN202110774098.6A patent/CN113849921B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378069A (en) * | 2019-08-01 | 2019-10-25 | 南京坤拓土木工程科技有限公司 | A method of prediction boring machine cutter accumulated quality loss late |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113849921A (en) | 2021-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113488117B (en) | Deep gold ore deposit ore-forming and prospecting method with deep learning capability | |
| CN110617074B (en) | Incidence relation method for ground settlement and tunneling parameters in shield construction | |
| CN113236228B (en) | Method and system for rapidly predicting single well yield | |
| CN112196559A (en) | TBM operation parameter optimization method based on optimal tunneling speed and optimal cutter consumption | |
| CN116520772A (en) | Sheet part numerical control machining quality prediction method based on multitasking transfer learning | |
| CN113741362A (en) | Method, system, medium, and computing device for optimizing operation of liquefied natural gas receiving station | |
| CN113849921B (en) | Method for evaluating pretreatment effect of large data sample of wear of cutter of tunneling machine | |
| CN108304975A (en) | A kind of data prediction system and method | |
| CN110991079A (en) | Oil and gas reservoir parameter interpretation method and device based on neural network and electronic equipment | |
| CN116305702A (en) | Method and system for analyzing data fluctuation shale gas well yield experience decreasing curve | |
| CN114357750A (en) | Goaf water filling state evaluation method | |
| CN113762614A (en) | Shale gas well productivity prediction method based on static oil and gas field data | |
| CN114004100A (en) | Oil reservoir assisted history fitting and optimization simulation method | |
| CN113420506A (en) | Method for establishing prediction model of tunneling speed, prediction method and device | |
| CN114117654A (en) | Horizontal well perforation optimization design method and device based on machine learning | |
| CN113027433A (en) | Method and device for calculating permeability of strong heterogeneous glutenite reservoir | |
| CN111580179B (en) | Method, device and system for determining organic carbon content | |
| CN117312919A (en) | Rock burst early warning method based on BO-CNN-LSTM model | |
| CN107679330B (en) | Real-time evaluation method for rock breaking performance loss degree of TBM cutter head system | |
| CN114818493A (en) | Method for quantitatively evaluating integrity degree of tunnel rock mass | |
| CN114331071A (en) | Model training method, fracturing parameter determination device and computer equipment | |
| CN113158562A (en) | TBM rock machine mapping construction method and system based on physical constraint and data mining | |
| CN111861944B (en) | Nuclide energy spectrum peak searching method based on morphology of multi-structure elements | |
| CN114183134B (en) | Shale gas horizontal well ground stress prediction method and system | |
| CN115110962B (en) | Method and system for predicting shield tunneling parameters of composite stratum with different composite ratios |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |